11 accepted papers
Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks: adversarial instructions hidden in interface elements that persuad…
Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real-world execution, due to varied categories and shapes, complex dynamics…
3D single object tracking based on point clouds is a key challenge in robotics and autonomous driving technology. Mainstream methods rely on point clouds for geometric matching or motion estimation between the target template and the search area. However, the lack of texture and the sparsity of inco
Conventional imitation learning (IL) struggles with scalability and catastrophic forgetting in sequential task learning, prompting the need for Lifelong Imitation Learning (LIL) to enable sustainable knowledge accumulation. However, existing LIL approaches, which largely depend on replaying demonstr
Safety fine-tuning algorithms reduce harmful outputs in language models, yet their mechanisms remain under-explored. Direct Preference Optimization (DPO) is a popular choice of algorithm, but prior explanations—attributing its effects solely to dampened toxic neurons in the MLP layers—are incomplete
To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its prediction by modifying the input such that it would have p
Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as `safety' and `robustness' requires strong construct validity, that is, having measures t…
Sparse point-based trackers struggle with texture-less and incomplete point clouds. Conversely, dense voxel-based trackers have richer spatial and semantic information, but filtering out interference from complex backgrounds remains a challenge. Additionally, there is still a gap between point and v
3D single object tracking (SOT) based on point cloud has attracted much attention due to its important role in machine vision and autonomous driving. Recently, M2-Track proposes a two-stage tracking structure centered on motion, but they ignore the effect of segmentation errors in sparse point cloud…
LiDAR-based 3D single object tracking has received remarkable attention due to its crucial role in robotics and autonomous driving. Most of them are based on hierarchical feature structures from PointNet++. However, existing based-stratified structure trackers ignore the fact that non-linearities in